Build a website RAG support chatbot with Firecrawl, Pinecone, and Gemini

by Mohammad Abid ✓ · 5 views · created 2026-09-14 · Support Chatbot, AI RAG

What this workflow does

This AI workflow has 22 nodes and runs when someone submits an n8n form (“Crawl a Website”) (plus 1 other trigger). Along the way it connects Pinecone Vector Store, Embeddings Google Gemini, Google Gemini Chat Model and Firecrawl (community). It also calls api.pinecone.io over HTTP.

How it runs

Trigger: When someone submits an n8n form (“Crawl a Website”) (plus 1 other trigger).

1. Normalize Website URL (Edit Fields (Set)): sets 1 field: url
2. Customer Support Agent (AI Agent): runs an AI agent, with model: Google Gemini Chat Model; 1 tool (Pinecone Vector Storage); memory: Chat Memory
3. Get Pinecone Index Host (HTTP Request): calls api.pinecone.io
4. Clear Pinecone Namespace (HTTP Request): calls an HTTP API (POST)
5. Map Website URLs (Firecrawl): map (map search)
6. Filter and Normalize URLs (Code): runs custom JavaScript code
7. Process URLs One by One (Loop Over Items (Split in Batches)): loops over the items in batches
8. Rate Limit Delay (Wait): waits 2 seconds
9. Fetch Page Content (HTTP Request): calls an HTTP API
10. Extract HTML and URL (Edit Fields (Set)): sets 2 fields: html, url

…plus 4 more steps. See the full node list below.

Services it uses

Pinecone Vector StoreEmbeddings Google GeminiGoogle Gemini Chat ModelFirecrawl (community)

HTTP calls to: api.pinecone.io

Uses Firecrawl. New users get 10% off with our link.

Before you upgrade to n8n 3.0

Nodes used (15)

• n8n Form Triggern8n-nodes-base.formTrigger
• Edit Fields (Set)n8n-nodes-base.set
• HTTP Requestn8n-nodes-base.httpRequest
• Firecrawl@mendable/n8n-nodes-firecrawl.firecrawl
• Coden8n-nodes-base.code
• Loop Over Items (Split in Batches)n8n-nodes-base.splitInBatches
• Waitn8n-nodes-base.wait
• Ifn8n-nodes-base.if
• Pinecone Vector Store@n8n/n8n-nodes-langchain.vectorStorePinecone
• Embeddings Google Gemini@n8n/n8n-nodes-langchain.embeddingsGoogleGemini
• Default Data Loader@n8n/n8n-nodes-langchain.documentDefaultDataLoader
• Chat Trigger@n8n/n8n-nodes-langchain.chatTrigger
• AI Agent@n8n/n8n-nodes-langchain.agent
• Google Gemini Chat Model@n8n/n8n-nodes-langchain.lmChatGoogleGemini
• Simple Memory@n8n/n8n-nodes-langchain.memoryBufferWindow

From the author

Quick overview This template indexes a website into Pinecone using Firecrawl, Google Gemini embeddings, and basic HTML cleaning, then exposes a public n8n chat webhook where a Gemini-powered agent answers customer questions by retrieving relevant website…

View the original on n8n.io → Check your own copy